Unlock instant, AI-driven research and patent intelligence for your innovation.

An artificial neural network controller based on master-slave neurons

A technology of artificial neural network and neuron, applied in the field of artificial neural network controller

Active Publication Date: 2022-06-21
TSINGHUA UNIV
View PDF17 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although some scientists have proposed a method for artificial neural network evolution and learning new tasks in terms of algorithm architecture, there is no relevant hardware to implement this method at present.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An artificial neural network controller based on master-slave neurons
  • An artificial neural network controller based on master-slave neurons
  • An artificial neural network controller based on master-slave neurons

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The invention proposes an artificial neural network controller based on Master-Slave neurons, the structure is as follows figure 1 As shown, it includes: a Master neuron module, a plurality of independent Slave neuron modules and a non-volatile memristor array; wherein, the Master neuron module includes a plurality of independent Master neurons, each Master neuron respectively connect the non-volatile memristor array and each Slave neuron module, and the non-volatile memristor array is respectively connected to each Slave neuron module;

[0019] Each master neuron in the master neuron module is used for receiving the coded external input voltage signal, and then sending the voltage signal to the corresponding non-volatile memristor in the non-volatile memristor array.

[0020] The non-volatile memristor array is used to receive the voltage signal sent by the corresponding master neuron, and then send the voltage signal to each slave neuron module.

[0021] Each of the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention proposes an artificial neural network controller based on Master-Slave neurons, which belongs to the technical field of artificial neural network hardware implementation. The controller includes: a Master neuron module, a plurality of independent Slave neuron modules and a non-volatile memristor array; wherein, the Master neuron module includes a plurality of independent Master neurons, and each Master neuron The non-volatile memristor array is respectively connected to each Slave neuron module, and the non-volatile memristor array is respectively connected to each Slave neuron module. After the Master neuron of the present invention receives the new task information, under the premise of not changing the trained information preserved by the neural network, the new information is learned by training the new Slave neuron, so that the artificial neural network has a function like Adaptive and learning capabilities like biological neural networks.

Description

technical field [0001] The invention belongs to the technical field of artificial neural network hardware implementation, and particularly proposes an artificial neural network controller based on Master-Slave neurons. Background technique [0002] Artificial neural networks inspired by the neuron and synaptic cascade structure of the brain's neural network have shown very powerful capabilities in the fields of image and speech recognition. Moreover, this cascaded computing architecture of artificial neural networks is also considered to be the most effective way to solve the storage wall problem encountered by von Neumann computing architectures when processing large amounts of information. The ability of artificial neural networks to process information has further stimulated the enthusiasm for learning from nature, biology and human brains in the field of artificial intelligence. The ability to adapt and learn to new things and new environments is the key to human surviv...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 李辛毅吴华强钱鹤
Owner TSINGHUA UNIV